Ordination

library("phyloseq"); packageVersion("phyloseq")
## [1] '1.32.0'
data(GlobalPatterns)
library("ggplot2"); packageVersion("ggplot2")
## [1] '3.3.2'
library("plyr"); packageVersion("plyr")
## [1] '1.8.6'
  1. Filter low-occurance and poorly represented OTUs.

Remove OTUs that do not appear more than five times in more than half the samples.

GP = GlobalPatterns
wh0 = genefilter_sample(GP, filterfun_sample(function(x) x > 5), A=0.5*nsamples(GP))
GP1 = prune_taxa(wh0, GP)

Transform to even sampling depth

GP1 = transform_sample_counts(GP1, function(x) 1E6 * x/sum(x))

Keep only the most abundant five phyla.

phylum.sum = tapply(taxa_sums(GP1), tax_table(GP1)[, "Phylum"], sum, na.rm=TRUE)
top5phyla = names(sort(phylum.sum, TRUE))[1:5]
GP1 = prune_taxa((tax_table(GP1)[, "Phylum"] %in% top5phyla), GP1)
human = get_variable(GP1, "SampleType") %in% c("Feces", "Mock", "Skin", "Tongue")
sample_data(GP1)$human <- factor(human)

Four main ordination plots

(1) Just OTUs

GP.ord <- ordinate(GP1, "NMDS", "bray")
## Square root transformation
## Wisconsin double standardization
## Run 0 stress 0.1333468 
## Run 1 stress 0.1448829 
## Run 2 stress 0.1513368 
## Run 3 stress 0.1624911 
## Run 4 stress 0.1527474 
## Run 5 stress 0.168418 
## Run 6 stress 0.373952 
## Run 7 stress 0.1821129 
## Run 8 stress 0.1789908 
## Run 9 stress 0.1385323 
## Run 10 stress 0.1465222 
## Run 11 stress 0.1455344 
## Run 12 stress 0.1570723 
## Run 13 stress 0.3809872 
## Run 14 stress 0.1570722 
## Run 15 stress 0.1507941 
## Run 16 stress 0.1385323 
## Run 17 stress 0.1529609 
## Run 18 stress 0.1497848 
## Run 19 stress 0.1385324 
## Run 20 stress 0.168475 
## *** No convergence -- monoMDS stopping criteria:
##     19: stress ratio > sratmax
##      1: scale factor of the gradient < sfgrmin
p1 = plot_ordination(GP1, GP.ord, type="taxa", color="Phylum", title="taxa")
print(p1)

p1 + facet_wrap(~Phylum, 3)

(2) Just Samples

  • Shade the points by “SampleType” while also modifying the shape according to whether they are human-associated.
p2 = plot_ordination(GP1, GP.ord, type="samples", color="SampleType", shape="human") 
p2 + geom_polygon(aes(fill=SampleType)) + geom_point(size=5) + ggtitle("samples")

(3) Biplot graphic

  • plot ordination - create two different graphic layouts in which both the samples and OTUs are plotted together in one “biplot”.
p3 = plot_ordination(GP1, GP.ord, type="biplot", color="SampleType", shape="Phylum", title="biplot")
# Some stuff to modify the automatic shape scale
GP1.shape.names = get_taxa_unique(GP1, "Phylum")
GP1.shape <- 15:(15 + length(GP1.shape.names) - 1)
names(GP1.shape) <- GP1.shape.names
GP1.shape["samples"] <- 16
p3 + scale_shape_manual(values=GP1.shape)

(4) Split graphic

p4 = plot_ordination(GP1, GP.ord, type="split", color="Phylum", shape="human", label="SampleType", title="split") 
p4

gg_color_hue <- function(n){
    hues = seq(15, 375, length=n+1)
    hcl(h=hues, l=65, c=100)[1:n]
}
color.names <- levels(p4$data$Phylum)
p4cols <- gg_color_hue(length(color.names))
names(p4cols) <- color.names
p4cols["samples"] <- "black"
p4 + scale_color_manual(values=p4cols)

Supported Ordination Methods

dist = "bray"
ord_meths = c("DCA", "CCA", "RDA", "DPCoA", "NMDS", "MDS", "PCoA")
plist = llply(as.list(ord_meths), function(i, physeq, dist){
        ordi = ordinate(physeq, method=i, distance=dist)
        plot_ordination(physeq, ordi, "samples", color="SampleType")
}, GP1, dist)
## Square root transformation
## Wisconsin double standardization
## Run 0 stress 0.1333468 
## Run 1 stress 0.1502708 
## Run 2 stress 0.1460271 
## Run 3 stress 0.146027 
## Run 4 stress 0.2546625 
## Run 5 stress 0.1470663 
## Run 6 stress 0.1333468 
## ... Procrustes: rmse 2.062125e-05  max resid 6.067958e-05 
## ... Similar to previous best
## Run 7 stress 0.1333468 
## ... New best solution
## ... Procrustes: rmse 6.297503e-06  max resid 1.88958e-05 
## ... Similar to previous best
## Run 8 stress 0.1505794 
## Run 9 stress 0.1673159 
## Run 10 stress 0.1610051 
## Run 11 stress 0.1477687 
## Run 12 stress 0.1385323 
## Run 13 stress 0.1529609 
## Run 14 stress 0.1333468 
## ... New best solution
## ... Procrustes: rmse 3.738317e-06  max resid 1.124261e-05 
## ... Similar to previous best
## Run 15 stress 0.1455344 
## Run 16 stress 0.1539741 
## Run 17 stress 0.1460271 
## Run 18 stress 0.1613714 
## Run 19 stress 0.1507641 
## Run 20 stress 0.1470663 
## *** Solution reached
names(plist) <- ord_meths
pdataframe = ldply(plist, function(x){
    df = x$data[, 1:2]
    colnames(df) = c("Axis_1", "Axis_2")
    return(cbind(df, x$data))
})
names(pdataframe)[1] = "method"
p = ggplot(pdataframe, aes(Axis_1, Axis_2, color=SampleType, shape=human, fill=SampleType))
p = p + geom_point(size=4) + geom_polygon()
p = p + facet_wrap(~method, scales="free")
p = p + scale_fill_brewer(type="qual", palette="Set1")
p = p + scale_colour_brewer(type="qual", palette="Set1")
p

plist[[2]] 

p = plist[[2]] + scale_colour_brewer(type="qual", palette="Set1")
p = p + scale_fill_brewer(type="qual", palette="Set1")
p = p + geom_point(size=5) + geom_polygon(aes(fill=SampleType))
p

MDS (“PCoA”) on Unifrac Distances

ordu = ordinate(GP1, "PCoA", "unifrac", weighted=TRUE)
plot_ordination(GP1, ordu, color="SampleType", shape="human")

p = plot_ordination(GP1, ordu, color="SampleType", shape="human")
p = p + geom_point(size=7, alpha=0.75)
p = p + scale_colour_brewer(type="qual", palette="Set1")
p + ggtitle("MDS/PCoA on weighted-UniFrac distance, GlobalPatterns")

———————————————————————————————

Global Patterns

library("phyloseq"); packageVersion("phyloseq")
## [1] '1.32.0'
data("GlobalPatterns")
library("ggplot2"); packageVersion("ggplot2")
## [1] '3.3.2'
theme_set(theme_bw())
pal = "Set1"
scale_colour_discrete <-  function(palname=pal, ...){
  scale_colour_brewer(palette=palname, ...)
}
scale_fill_discrete <-  function(palname=pal, ...){
  scale_fill_brewer(palette=palname, ...)
}
GP <- prune_species(speciesSums(GlobalPatterns) > 0, GlobalPatterns)
## Warning: 'prune_species' is deprecated.
## Use 'prune_taxa' instead.
## See help("Deprecated") and help("phyloseq-deprecated").
## Warning: 'speciesSums' is deprecated.
## Use 'taxa_sums' instead.
## See help("Deprecated") and help("phyloseq-deprecated").

Plot Examples

plot_richness(GP)

plot_richness(GP, measures=c("Chao1", "Shannon"))

plot_richness(GP, x="SampleType", measures=c("Chao1", "Shannon"))

sampleData(GP)$human <- getVariable(GP, "SampleType") %in% c("Feces", "Mock", "Skin", "Tongue")
## Warning: 'getVariable' is deprecated.
## Use 'get_variable' instead.
## See help("Deprecated") and help("phyloseq-deprecated").
## Warning: 'sampleData' is deprecated.
## Use 'sample_data' instead.
## See help("Deprecated") and help("phyloseq-deprecated").
## Warning: 'sampleData<-' is deprecated.
## Use 'sample_data<-' instead.
## See help("Deprecated") and help("phyloseq-deprecated").
plot_richness(GP, x="human", color="SampleType", measures=c("Chao1", "Shannon"))

GPst = merge_samples(GP, "SampleType")
# repair variables that were damaged during merge (coerced to numeric)
sample_data(GPst)$SampleType <- factor(sample_names(GPst))
sample_data(GPst)$human <- as.logical(sample_data(GPst)$human)
p = plot_richness(GPst, x="human", color="SampleType", measures=c("Chao1", "Shannon"))
p + geom_point(size=5, alpha=0.7)

Heat Maps

Plot a 300-taxa dataset

data("GlobalPatterns")
gpt <- subset_taxa(GlobalPatterns, Kingdom=="Bacteria")
gpt <- prune_taxa(names(sort(taxa_sums(gpt),TRUE)[1:300]), gpt)
plot_heatmap(gpt, sample.label="SampleType")
## Warning: Transformation introduced infinite values in discrete y-axis

## Subset a smaller dataset based on an Archaeal phylum

gpac <- subset_taxa(GlobalPatterns, Phylum=="Crenarchaeota")
plot_heatmap(gpac)
## Warning: Transformation introduced infinite values in discrete y-axis

### Re-label by a sample variable and taxonomic family

(p <- plot_heatmap(gpac, "NMDS", "bray", "SampleType", "Family"))
## Warning: Transformation introduced infinite values in discrete y-axis

Re-label axis titles

p$scales$scales[[1]]$name <- "My X-Axis"
p$scales$scales[[2]]$name <- "My Y-Axis"
print(p)
## Warning: Transformation introduced infinite values in discrete y-axis

Changing the color scheme

plot_heatmap(gpac, "NMDS", "bray", "SampleType", "Family", low="#000033", high="#CCFF66")
## Warning: Transformation introduced infinite values in discrete y-axis

plot_heatmap(gpac, "NMDS", "bray", "SampleType", "Family", low="#FFFFCC", high="#000033", na.value="white")
## Warning: Transformation introduced infinite values in discrete y-axis

Different ecological distances/ordinations

plot_heatmap(gpac, "MDS", "unifrac", "SampleType", "Family", weighted=TRUE)
## Warning: Transformation introduced infinite values in discrete y-axis